KVM: PPC: Book3S: MMIO emulation support for little endian guests

MMIO emulation reads the last instruction executed by the guest
and then emulates. If the guest is running in Little Endian order,
or more generally in a different endian order of the host, the
instruction needs to be byte-swapped before being emulated.

This patch adds a helper routine which tests the endian order of
the host and the guest in order to decide whether a byteswap is
needed or not. It is then used to byteswap the last instruction
of the guest in the endian order of the host before MMIO emulation
is performed.

Finally, kvmppc_handle_load() of kvmppc_handle_store() are modified
to reverse the endianness of the MMIO if required.
Signed-off-by: Cédric Le Goater <clg@fr.ibm.com>
[agraf: add booke handling]
Signed-off-by: Alexander Graf <agraf@suse.de>

arch/powerpc/include/asm/kvm_book3s.h

@@ -264,6 +264,11 @@ static inline ulong kvmppc_get_pc(struct kvm_vcpu *vcpu)
 	return vcpu->arch.pc;
 }
 
+static inline bool kvmppc_need_byteswap(struct kvm_vcpu *vcpu)
+{
+	return (vcpu->arch.shared->msr & MSR_LE) != (MSR_KERNEL & MSR_LE);
+}
+
 static inline u32 kvmppc_get_last_inst_internal(struct kvm_vcpu *vcpu, ulong pc)
 {
 	/* Load the instruction manually if it failed to do so in the
@@ -271,7 +276,8 @@ static inline u32 kvmppc_get_last_inst_internal(struct kvm_vcpu *vcpu, ulong pc)
 	if (vcpu->arch.last_inst == KVM_INST_FETCH_FAILED)
 		kvmppc_ld(vcpu, &pc, sizeof(u32), &vcpu->arch.last_inst, false);
 
-	return vcpu->arch.last_inst;
+	return kvmppc_need_byteswap(vcpu) ? swab32(vcpu->arch.last_inst) :
+		vcpu->arch.last_inst;
 }
 
 static inline u32 kvmppc_get_last_inst(struct kvm_vcpu *vcpu)

arch/powerpc/include/asm/kvm_booke.h

@@ -63,6 +63,12 @@ static inline u32 kvmppc_get_xer(struct kvm_vcpu *vcpu)
 	return vcpu->arch.xer;
 }
 
+static inline bool kvmppc_need_byteswap(struct kvm_vcpu *vcpu)
+{
+	/* XXX Would need to check TLB entry */
+	return false;
+}
+
 static inline u32 kvmppc_get_last_inst(struct kvm_vcpu *vcpu)
 {
 	return vcpu->arch.last_inst;

arch/powerpc/include/asm/kvm_ppc.h

@@ -54,12 +54,13 @@ extern void kvmppc_handler_highmem(void);
 extern void kvmppc_dump_vcpu(struct kvm_vcpu *vcpu);
 extern int kvmppc_handle_load(struct kvm_run *run, struct kvm_vcpu *vcpu,
                               unsigned int rt, unsigned int bytes,
-                              int is_bigendian);
+			      int is_default_endian);
 extern int kvmppc_handle_loads(struct kvm_run *run, struct kvm_vcpu *vcpu,
                                unsigned int rt, unsigned int bytes,
-                               int is_bigendian);
+			       int is_default_endian);
 extern int kvmppc_handle_store(struct kvm_run *run, struct kvm_vcpu *vcpu,
-                               u64 val, unsigned int bytes, int is_bigendian);
+			       u64 val, unsigned int bytes,
+			       int is_default_endian);
 
 extern int kvmppc_emulate_instruction(struct kvm_run *run,
                                       struct kvm_vcpu *vcpu);

arch/powerpc/kvm/book3s_64_mmu_hv.c

@@ -558,7 +558,7 @@ static int kvmppc_hv_emulate_mmio(struct kvm_run *run, struct kvm_vcpu *vcpu,
 	 * we just return and retry the instruction.
 	 */
 
-	if (instruction_is_store(vcpu->arch.last_inst) != !!is_store)
+	if (instruction_is_store(kvmppc_get_last_inst(vcpu)) != !!is_store)
 		return RESUME_GUEST;
 
 	/*

arch/powerpc/kvm/emulate.c

@@ -219,7 +219,6 @@ static int kvmppc_emulate_mfspr(struct kvm_vcpu *vcpu, int sprn, int rt)
  * lmw
  * stmw
  *
- * XXX is_bigendian should depend on MMU mapping or MSR[LE]
  */
 /* XXX Should probably auto-generate instruction decoding for a particular core
  * from opcode tables in the future. */

arch/powerpc/kvm/powerpc.c

@@ -673,9 +673,19 @@ static void kvmppc_complete_mmio_load(struct kvm_vcpu *vcpu,
 }
 
 int kvmppc_handle_load(struct kvm_run *run, struct kvm_vcpu *vcpu,
-                       unsigned int rt, unsigned int bytes, int is_bigendian)
+		       unsigned int rt, unsigned int bytes,
+		       int is_default_endian)
 {
 	int idx, ret;
+	int is_bigendian;
+
+	if (kvmppc_need_byteswap(vcpu)) {
+		/* Default endianness is "little endian". */
+		is_bigendian = !is_default_endian;
+	} else {
+		/* Default endianness is "big endian". */
+		is_bigendian = is_default_endian;
+	}
 
 	if (bytes > sizeof(run->mmio.data)) {
 		printk(KERN_ERR "%s: bad MMIO length: %d\n", __func__,
@@ -711,21 +721,31 @@ EXPORT_SYMBOL_GPL(kvmppc_handle_load);
 
 /* Same as above, but sign extends */
 int kvmppc_handle_loads(struct kvm_run *run, struct kvm_vcpu *vcpu,
-                        unsigned int rt, unsigned int bytes, int is_bigendian)
+			unsigned int rt, unsigned int bytes,
+			int is_default_endian)
 {
 	int r;
 
 	vcpu->arch.mmio_sign_extend = 1;
-	r = kvmppc_handle_load(run, vcpu, rt, bytes, is_bigendian);
+	r = kvmppc_handle_load(run, vcpu, rt, bytes, is_default_endian);
 
 	return r;
 }
 
 int kvmppc_handle_store(struct kvm_run *run, struct kvm_vcpu *vcpu,
-                        u64 val, unsigned int bytes, int is_bigendian)
+			u64 val, unsigned int bytes, int is_default_endian)
 {
 	void *data = run->mmio.data;
 	int idx, ret;
+	int is_bigendian;
+
+	if (kvmppc_need_byteswap(vcpu)) {
+		/* Default endianness is "little endian". */
+		is_bigendian = !is_default_endian;
+	} else {
+		/* Default endianness is "big endian". */
+		is_bigendian = is_default_endian;
+	}
 
 	if (bytes > sizeof(run->mmio.data)) {
 		printk(KERN_ERR "%s: bad MMIO length: %d\n", __func__,